Exposed Hugging Face API tokens jeopardized GenAI models

Lasso Security researchers discovered 1,681 Hugging Face API tokens exposed in code repositories, which left vendors such as Google, Meta, Microsoft and VMware open to potential supply chain attacks.
In a blog post published Monday, Lasso Security said the exposed API tokens gave its researchers access to 723 organizations' GitHub and Hugging Face repositories, which contained high-value data on large language models and generative AI projects.
Hugging Face, a data science community and development platform, says it hosts more than 500,000 AI models and 250,000 data sets.
According to Lasso Security, the exposed API tokens left organizations' GenAI models and data sets open to a variety of threats, including supply chain attacks, poisoning of training data and theft of models.
Bar Lanyado, security researcher at Lasso, wrote that 655 organizations' tokens had write permissions, which gave the researchers full access to the repositories.
Some of the repositories that were open to full access were for platforms and LLMs such as the open source Meta Llama 2, EleutherAI's Pythia and BigScience Workshop's Bloom.
In a statement to TechTarget Editorial, Hugging Face said all exposed API tokens have been revoked, but the company appeared to put the blame primarily on customers.
Lanyado wrote that Hugging Face bears responsibility as well, and recommended that it continually scan for exposed API tokens and either revoke them directly or notify users.
Lanyado credited several organizations with fast responses to Lasso Security's findings.
Hugging Face said it is working on measures that will better prevent other exposures in the future.
Lanyado said the researchers ran into obstacles while searching code by regular expressions; the initial search produced only the first 100 results on GitHub.
The researchers then searched for HuggingFace API tokens regex for both users and org api tokens, which returned thousands of results.
Exposed API tokens were even more difficult to scan for on Hugging Face, Lanyado said, as the platform did not allow searches by regex.
Instead, the researchers searched for API tokens by substrings.
The researchers found another issue related to Hugging Face's org api tokens.
The company had previously deprecated those tokens and also blocked their usage in its Python library by checking the token type in the login function.
Even though the tokens had been deprecated, researchers found they could use exposed org api tokens to download private models from repositories.
Lanyado said researchers gained the ability to read and download a private LLM model from Microsoft.
Rob Wright is a longtime technology reporter who lives in the Boston area.


This Cyber News was published on www.techtarget.com. Publication date: Tue, 05 Dec 2023 20:13:05 +0000


Cyber News related to Exposed Hugging Face API tokens jeopardized GenAI models

Exposed Hugging Face API tokens jeopardized GenAI models - Lasso Security researchers discovered 1,681 Hugging Face API tokens exposed in code repositories, which left vendors such as Google, Meta, Microsoft and VMware open to potential supply chain attacks. In a blog post published Monday, Lasso Security ...
11 months ago Techtarget.com
Meta AI Models Cracked Open With Exposed API Tokens - Researchers recently were able to get full read and write access to Meta's Bloom, Meta-Llama, and Pythia large language model repositories in a troubling demonstration of the supply chain risks to organizations using these repositories to integrate ...
11 months ago Darkreading.com
Hugging Face dodged a cyber-bullet with Lasso Security's help - Further validating how brittle the security of generative AI models and their platforms are, Lasso Security helped Hugging Face dodge a potentially devastating attack by discovering that 1,681 API tokens were at risk of being compromised. The tokens ...
11 months ago Venturebeat.com
Exposed Hugging Face APIs Opened AI Models to Cyberattacks - Security flaws found in both Hugging Face and GitHub repositories exposed almost 1,700 API tokens, opening up AI developers to supply chain and other attacks and putting a brighter spotlight on the need to ensure that security keeps up with the ...
11 months ago Securityboulevard.com
Hugging Face API tokens exposed, major projects vulnerable The Register - The API tokens of tech giants Meta, Microsoft, Google, VMware, and more have been found exposed on Hugging Face, opening them up to potential supply chain attacks. Researchers at Lasso Security found more than 1,500 exposed API tokens on the open ...
11 months ago Go.theregister.com
Major Organizations Using 'Hugging Face' AI Tools Put at Risk by Leaked API Tokens - AI cybersecurity startup Lasso has discovered more than 1,600 valid Hugging Face API tokens exposed in code repositories, providing access to hundreds of organizations' accounts. Leaked secrets, such as tokens, have long been the focus of ...
11 months ago Securityweek.com
Aim Security Raises $10M to Secure Generative AI Enterprise Adoption - PRESS RELEASE. TEL AVIV, Israel-(BUSINESS WIRE)-Aim Security, an Israeli cybersecurity startup offering enterprises a holistic, one-stop shop GenAI security platform, today announced $10 million in seed funding. Aim Security was founded by ...
9 months ago Darkreading.com
In the rush to build AI apps, don't leave security behind The Register - There are countless models, libraries, algorithms, pre-built tools, and packages to play with, and progress is relentless. You'll typically glue together libraries, packages, training data, models, and custom source code to perform inference tasks. ...
7 months ago Go.theregister.com
AI platform Hugging Face says hackers stole auth tokens from Spaces - AI platform Hugging Face says that its Spaces platform was breached, allowing hackers to access authentication secrets for its members. Hugging Face Spaces is a repository of AI apps created and submitted by the community's users, allowing other ...
5 months ago Bleepingcomputer.com
Akto Launches Proactive GenAI Security Testing Solution - With the increasing reliance on GenAI models and Language Learning Models like ChatGPT, the need for robust security measures have become paramount. Akto, a leading API Security company, is proud to announce the launch of its revolutionary GenAI ...
8 months ago Darkreading.com
Flow Security Launches GenAI DLP - PRESS RELEASE. TEL AVIV, Israel, Nov. 30, 2023 /PRNewswire/ - Flow Security, the pioneering Data Security Lifecycle Platform, announced today its extension to GenAI Security with the launch of a new GenAI DLP module. This move makes Flow Security the ...
11 months ago Darkreading.com
GenAI Regulation: Why It Isn't One Size Fits All - With President Biden calling on Congress to pass bipartisan data privacy legislation to accelerate the development and use of privacy-centric techniques for the data that is training AI, it's important to remember that excessive regulation can stifle ...
7 months ago Cybersecurity-insiders.com
AI Market Research: The Pivotal Role of Generative AI in Cyber Security - What researchers are learning about GenAI and cyber security. Pair AI with cyber security and the possibilities are staggering. For many security professionals, it's a foregone conclusion that incorporating intelligence into cyber security will ...
5 months ago Blog.checkpoint.com
ML Model Repositories: The Next Big Supply Chain Attack Target - The techniques are similar to ones that attackers have successfully used for years to upload malware to open source code repositories, and highlight the need for organizations to implement controls for thoroughly inspecting ML models before use. ...
7 months ago Darkreading.com
Cisco Motific reduces GenAI security, trust, and compliance risks - Cisco announced Motific, Cisco's SaaS product that allows for trustworthy GenAI deployments in organizations. Born from Outshift, Cisco's incubation business, Motific provides a central view across the entire GenAI journey, empowering central IT and ...
9 months ago Helpnetsecurity.com
Hugging Face's AI Supply Chain Escapes Near Breach by Hackers - A recent report from VentureBeat reveals that HuggingFace, a prominent AI leader specializing in pre-trained models and datasets, narrowly escaped a potential devastating cyberattack on its supply chain. The incident underscores existing ...
11 months ago Cysecurity.news
Defining Good: A Strategic Approach to API Risk Reduction - A good API security strategy starts with a well thought out API security posture governance program that spans from design to deployment. That standard, if communicated and enforced effectively, will not only positively affect how a developer designs ...
9 months ago Securityboulevard.com
Protect AI Unveils Gateway to Secure AI Models - Protect AI today launched a Guardian gateway that enables organizations to enforce security policies to prevent malicious code from executing within an artificial intelligence model. Guardian is based on ModelScan, an open source tool from Protect AI ...
9 months ago Securityboulevard.com
11 GenAI cybersecurity surveys you should read - Generative AI stands at the forefront of technological innovation, reshaping industries and unlocking new possibilities across various domains. As the integration of these technologies continues, a vigilant approach to ethical considerations and ...
10 months ago Helpnetsecurity.com
CISOs Reconsider Their Roles in Response to GenAI Integration - Chief information security officers face mounting pressure as cyberattacks surge and complexities surrounding the implementation of GenAI and AI technologies emerge. The vast majority - 92% - of the 500 CISOs surveyed by Trellix admitted they are ...
5 months ago Securityboulevard.com
That time I broke into an API and became a billionaire - This included an internal API with a dependency on a third-party banking API. We'll get to the banking API later in this story. That's all thanks to developers embracing agile development, microservices, and API gateway redirection that exposed ...
10 months ago Securityboulevard.com
Legal, compliance and privacy leaders anxious about rapid GenAI adoption - Rapid GenAI adoption is the top-ranked issue for the next two years for legal, compliance and privacy leaders, according to Gartner. 70% of respondents reported rapid GenAI adoption as a top concern for them. Gartner experts have identified four key ...
10 months ago Helpnetsecurity.com
Businesses gain upper hand with GenAI integration - Firms that actively harness generative AI to enhance experiences, offerings, and productivity will realize outsized growth and will outpace their competition, according to Forrester. Between July and September 2023, the number of enterprises that are ...
11 months ago Helpnetsecurity.com
Salt Security Delivers API Posture Governance Engine - PRESS RELEASE. PALO ALTO, Calif., Jan. 17, 2024 /PRNewswire/ - Salt Security, the leading API security company, today announced multiple advancements in discovery, posture management and AI-based threat protection to the industry leading Salt ...
9 months ago Darkreading.com
Why Tokens Are Like Gold for Opportunistic Threat Actors - COMMENTARY. Authentication tokens aren't actual physical tokens, of course. Authentication tokens are an important part of cybersecurity. Which means that anyone with a token has a gold key to corporate systems - without requiring a multifactor ...
5 months ago Darkreading.com

Latest Cyber News


Cyber Trends (last 7 days)


Trending Cyber News (last 7 days)